Claim Missing Document
Check
Articles

Tinjaun Literatur Sistematis Terhadap Teknologi Kecerdasan Buatan untuk Deteksi Nyeri (2020-2024) Dharma, Abdi; Veron, Veron; Wijaya, Jeremy; Valentino, Bue; Wijaya, Vincent
METIK JURNAL (AKREDITASI SINTA 3) Vol. 9 No. 1 (2025): METIK Jurnal
Publisher : LPPM Universitas Mulia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47002/metik.v9i1.1068

Abstract

Pain is a complex sensory and emotional experience, often difficult to assess objectively. In recent years, artificial intelligence (AI) has shown great potential in improving the accuracy and efficiency of pain assessment. This study aims to conduct a systematic review of AI-based pain detection methods developed in the period 2020 to 2024. Using the PRISMA 2020 approach, a literature search was conducted in three major databases: PubMed, Scopus, and Google Scholar, with keywords related to pain detection and perception. Of the 1,685 articles found, 44 studies were selected through a rigorous selection process. The analysis of five showed the main approaches in pain detection: Neuroimaging & Neurological, Physiological & Biometric, Visual-Only (facial recognition), Audio/Speech-based, and Behavioral/Observational. Neuroimaging-based approaches such as EEG and fMRI were the most dominant, followed by the use of biometric sensors and facial recognition technology. However, significant challenges remain, including the limitations of global data standards, difficulties in model generalization, and ethical and privacy issues. This study highlights that the integration of non-invasive sensors with deep learning models and personalized approaches can improve the effectiveness of automated pain detection systems.
Tren dan Potensi Sistem Informasi Geografis dalam Penanggulangan Demam Berdarah: Analisis Bibliometrik Crispin, Andrian Reinaldo; Edbert, Edbert; Hulu, Victor Trismanjaya; Kamble, Pratik Bibhisan; Dharma, Abdi
Data Sciences Indonesia (DSI) Vol. 5 No. 1 (2025): Article Research Volume 5 Issue 1, June 2025
Publisher : Yayasan Cita Cendikiawan Al Kharizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/dsi.v5i1.6351

Abstract

Demam berdarah dengue masih menjadi masalah kesehatan masyarakat yang signifikan di banyak negara. Tingginya prevalensi penyakit ini menunjukkan perlunya alat yang efektif seperti Sistem Informasi Geografis (SIG) untuk membantu memprediksi dan mengelola penyebarannya. Penelitian ini bertujuan untuk mengkaji dan merangkum peran SIG dalam pemetaan dan komunikasi pola transmisi dengue. Metode yang digunakan adalah pendekatan bibliometrik dengan pengumpulan literatur relevan dari beberapa basis data, seperti Google Scholar, Scopus, dan PubMed. Dari total 440 artikel yang diidentifikasi, hanya 11 yang memenuhi kriteria inklusi. Data yang dikumpulkan mencakup tahun publikasi (2013–2023), judul jurnal, desain studi, populasi, intervensi, hasil, serta manfaat yang dilaporkan dari penggunaan SIG dalam penelitian terkait dengue. Analisis kualitatif dilakukan dengan mengorganisasi dan mempresentasikan temuan utama dari studi yang terpilih. Hasil menunjukkan bahwa SIG sangat berguna dalam mengidentifikasi area wabah saat ini, mendeteksi zona berisiko tinggi melalui klaster spasial, meningkatkan akurasi prediksi kasus, serta mendukung upaya surveilans secara berkelanjutan. Selain itu, SIG juga berkontribusi pada pengambilan keputusan yang lebih tepat dalam program pencegahan dan pengendalian dengue. Secara keseluruhan, SIG memainkan peran penting dalam memahami dinamika penyakit, memperkuat sistem peringatan dini, dan membimbing respons kesehatan masyarakat terhadap wabah dengue.
Trends and Potential of Geographic Information Systems in Dengue Management: Bibliometric Analysis Crispin, Andrian Reinaldo; Edbert, Edbert; Hulu, Victor Trismanjaya; Kamble, Pratik Bibhisan; Dharma, Abdi
Journal of Engineering and Science Application Vol. 2 No. 2 (2025): October
Publisher : Institute Of Advanced Knowledge and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69693/jesa.v2i2.32

Abstract

Dengue fever remains a significant public health issue in many countries. Its high prevalence highlights the need for effective tools like Geographic Information Systems (GIS) to help predict and manage the spread of the disease. This study aims to examine and summarize the role of GIS in mapping and communicating dengue transmission patterns. A bibliometric approach was used to collect relevant literature from databases such as Google Scholar, Scopus, and PubMed. Out of 440 identified articles, only 11 met the inclusion criteria. Data extracted included publication years (2013–2023), journal titles, study designs, populations, interventions, outcomes, and reported benefits of GIS in dengue-related research. Qualitative analysis was conducted by organizing and presenting key findings. The results show that GIS is valuable in identifying current outbreak areas, detecting high-risk zones through spatial clustering, improving the accuracy of case predictions, and supporting ongoing surveillance efforts. Additionally, GIS contributes to more informed decision-making in dengue prevention and control programs. Overall, GIS plays an essential role in understanding disease dynamics, enhancing early warning systems, and guiding public health responses to dengue outbreaks.
Uplift modeling VS conventional predictive model: A reliable machine learning model to solve employee turnover Wijaya, Davin; DS, Jumri Habbeyb; Barus, Samuelta; Pasaribu, Beriman; Sirbu, Loredana Ioana; Dharma, Abdi
International Journal of Artificial Intelligence Research Vol 5, No 1 (2021): June 2021
Publisher : Universitas Dharma Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1478.697 KB) | DOI: 10.29099/ijair.v4i2.169

Abstract

Employee turnover is the loss of talent in the workforce that can be costly for a company. Uplift modeling is one of the prescriptive methods in machine learning models that not only predict an outcome but also prescribe a solution. Recent studies are focusing on the conventional predictive models to predict employee turnover rather than uplift modeling. In this research, we analyze whether the uplifting model has better performance than the conventional predictive model in solving employee turnover. Performance comparison between the two methods was carried out by experimentation using two synthetic datasets and one real dataset. The results show that despite the conventional predictive model yields an average prediction accuracy of 84%; it only yields a success rate of 50% to target the right employee with a retention program on the three datasets. By contrast, the uplift model only yields an average accuracy of 67% but yields a consistent success rate of 100% in targeting the right employee with a retention program.
Analisis Tren dan Perkiraan Pandemi COVID-19 di Indonesia Menggunakan Peramalan Metode Prophet :Sebelum dan Sesudah Aturan New Normal Harahap, Mawaddah; Andika, Ahmad Zaki; Husein, Amir Mahmud; Dharma, Abdi
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 9 No 1: Februari 2022
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jtiik.2022914060

Abstract

Dalam menanggulangi penyebaran pandemi Covid-19 di Indonesia, pemerintah telah menetapkan PSBB dan aturan Normal Baru namun laju penyebaran pandemi terus meningkat dari waktu ke waktu. Selain itu, ketidakpastian akan berakhirnya pandemi ini berdampak pada perubahan kondisi sosial. Makalah ini bertujuan untuk memfasilitasi perbandingan antara PSBB dan regulasi New Normal tentang perkembangan jumlah kasus Covid-19 di Indonesia dengan memetakan jumlah kumulatif kasus (kasus aktif, sembuh, dikonfirmasi dan meninggal). Metode Prophet digunakan untuk memprediksi kasus kematian dan terkonfirmasi dalam 30 hari ke depan. Analisis data visual dengan pendekatan Exploratory Data Analysis (EDA) disajikan untuk memberikan pemahaman tentang perkembangan penyebaran pandemi di Indonesia. Pengujian kerangka analisis dilakukan dengan eksperimen untuk mengukur tingkat ketepatan prediksi metode Prophet dengan membagi kumpulan data historis periode 23 Maret 2020 - 31 Juli 2020, sedangkan data bulan terakhir dari kumpulan data periode 01 Agustus 2020 hingga 5 September 2020 digunakan sebagai target prediksi. Berdasarkan hasil pengujian metode Prophet memprediksi Indonesia akan mengalami peningkatan jumlah kasus terkonfirmasi sekitar 238.322 kasus dan kematian sekitar 9.609 hingga akhir September dengan tingkat kesalahan relatif dari estimasi yang dievaluasi dengan MAPE sekitar 23,9%. dan MAE sekitar 73,12 MAE. Hasil analisis visual penyebaran suatu pandemi juga disajikan dengan harapan dapat bermanfaat sebagai wawasan perkembangan jumlah kasus pandemi di Indonesia. Abstract In countering the spread of the Covid-19 pandemic in Indonesia, the government has set PSBB and New Normal rules but the rate of spread of the pandemic continues to increase from time to time. In addition, the uncertainty about the end of this pandemic has resulted in changing social conditions. This paper aims to facilitate a comparison between the PSBB and New Normal regulations on the development of the number of Covid-19 cases in Indonesia by mapping the cumulative number of cases (active, cured, confirmed and death cases). The Prophet method is used to predict confirmed cases and deaths within the next 30 days. Visual data analysis using the Exploratory Data Analysis (EDA) approach is presented to provide an understanding of the development of the pandemic spread in Indonesia. The testing analysis framework was carried out by experiments to measure the level of prediction accuracy of the prophet method by dividing the historical data set for the period 23 March 2020 - 31 July 2020, while the last month data from the data set for the period 01 August 2020 to 5 September 2020 were used as prediction targets. Based on the results of the Prophet method testing it is estimated that Indonesia will experience an increase in the number of confirmed cases around 238,322 and cases of death around 9,609 until the end of September with the relative error rate of estimates evaluated with MAPE around 23.9% and MAE around 73.12 MAE. The results of a visual analysis of the spread of a pandemic are also presented in the hope that they will be useful as an insight into the development of the number of pandemic cases in Indonesia.
Prediksi Gelombang Corona Dengan Metode Neural Network Andrian; Dicky; Jefika, Meliy; Kosasi, Hendrick; Prayogi, Gali; William; Dharma, Abdi
Jurnal Ilmu Komputer dan Sistem Informasi (JIKOMSI) Vol. 3 No. 2 (2020): Jurnal Ilmu Komputer dan Sistem Informasi
Publisher : Utility Project Solution

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.9767/jikomsi.v3i2.74

Abstract

Until recently the spread of COVID-19 is unstoppable. COVID-19 is caused by RNA Virus that spread widely between humans, mammals, and birds which cause respiratory, enteric, heart and neurologic diseases. Although it is known for respiratory infection, the virus through plasma or serum is also happen often. Therefore, there is still theoretical risk of the virus spreading through blood transfusion. Because there are more cases that shown no symptoms, worries about the spread of COVID-19 is increasing. Several attempts have been done for alleviate mortality rates like mask usage and lockdown quarantine. Neural network adapt on how a human brain works. One of neural network techniques is Multilayer Perceptron (MLP). In MLP, input data is received through one dimension and spread through network until an output is achieved. Every neuron connection on two neighboring layers have one dimensional value that determine the quality of that node. On every input data at each layer calculation is done by the weight of the layer, and then the result will be transformed by using non-linear formula that called as activation function. The result of this research is found by the help of two cross validation technic: GridSearchCV and KFold Cross Validation which gave each 0.943887 and 0.911341 score. The score is achieved using r2 which the best parameter of the model is determined as: relu, 0.1, (10,10), invscaling and lbfgs. Result showns that the proposed model can do the prediction well against the mortality rate of corona.
Implementasi Algoritma Advanced Encryption Standard pada Aplikasi Chatting berbasis Android Randi, Albert; Lazuardya , Kevin; Chandra, Suwito; Dharma, Abdi
Jurnal Ilmu Komputer dan Sistem Informasi (JIKOMSI) Vol. 3 No. 1 (2020): Jurnal Ilmu Komputer dan Sistem Informasi (JIKOMSI)
Publisher : Utility Project Solution

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.9767/jikomsi.v3i1.76

Abstract

Kriptografi adalah Sebuah teknik rahasia dalam penulisan, dengan karakter khusus, dengan menggunakan huruf dan karakter di luar bentuk aslinya, atau dengan metode-metode lain yang hanya dapat dipahami oleh pihak-pihak yang memproses kunci, juga semua hal yang ditulis dengan cara seperti ini. Dalam Mengirimkan pesan dari pengguna ke pengguna yang lain perlu dirahasiakan agar informasi tersebut aman dan tidak diketahui oleh orang lain. Informasi yang dikirimkan dapat dirahasiakan menggunakan kriptografi. Aplikasi chatting menerapkan algoritma advanced encryption standard untuk merahasiakan pesan yang akan dikirim dengan melakukan enkripsi sebelum pesan itu dikirim dan melakukan dekripsi setelah pesan diterima sehingga pesan aman. Pesan yang disimpan di kirim merupakan pesan yang terenkripsi sehingga tidak dapat dibaca jika tidak dilakukan dekripsi dengan kunci yang benar. Implementasi algoritma advanced encryption standard untuk keamanan aplikasi chatting berbasis android dirancang menggunakan bahasa kotlin.
Evaluasi Isolat Pseudomonad fluoresens Indigenus dari Rizosfir Berbagai Kultivar Tanaman Pisang Sehat di Lahan Endemik Penyakit Layu Fusarium untuk Pengendalian Penyakit Layu Fusarium: english Sulyanti, Eri; Habazar, Trimurti; Husin, Eti Farda; Nasir, Nasril; Dharma, Abdi
Jurnal Proteksi Tanaman (Journal of Plant Protection) Vol. 2 No. 2 (2018): December 2018
Publisher : Plant Protection Department, Faculty of Agriculture, Universitas Andalas

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25077/jpt.2.2.87-96.2018

Abstract

Fusarium wilt diseases caused by Fusarium oxysporum f sp cubense (Foc) is the most important diseases on banana in the world. Once Foc is present in the soil, it cannot be eliminated. The aim of research was to evaluate the potential of Pseudomonad fluorescens indigenous to control Fusarium wilt in planta. This experiment was arranged by completely randomized design with 17 treatments and 10 replications. Sixteen isolates of P. fluorescens indigenous had been successly taken from several different cultivars of banana rhizospheres at endemic area of Fusarium wilt in the centre of banana production in West Sumatra that were introduced to banana seedlings cv Cavendish inoculated with Foc. The variable observed were incubation period, percentage of leaf infection, discoloration of pseudostem and the intensity of damaged corms. The result showed that The PfCvP1 isolate (from rhizosphere of Cavendish at low altitude area) was the most effective to inhibit the development of Fusarium wilt: 97.89 % (prolong incubation period), 67.26 % (reduced infected leaves), 63.63 % (reduced damaged corm), and 72.62 % (reduced disclorotion of pseudostem) and increased plant growth.
Systematic Literature Review untuk Identifikasi Penggunaan Sensor dalam Deteksi Rasa Sakit Giawa, Priskila Veronika; Yohana Samosir, Devi; Romaito pane, Jesi; Silaban, Elvin Josafat; Dharma, Abdi
Jurnal Algoritma Vol 22 No 2 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-2.2544

Abstract

Objective pain detection is a major challenge in the medical field because pain is subjective and difficult to measure accurately, particularly in patients who are unable to communicate. This study aims to identify and analyze both sensor-based and non-sensor technologies used in pain detection, as well as to evaluate technological development trends in this domain. The methodology employed is a Systematic Literature Review (SLR) following the PRISMA protocol, involving rigorous search and selection processes across the Scopus, PubMed, and Google Scholar databases. Out of a total of 3,559 identified articles, 130 studies were selected after screening and quality assessment. All eligible articles were then analyzed by extracting information relevant to the research topic. The findings indicate that physiological sensors such as EDA, ECG, EMG, and EEG, along with non-sensor technologies such as facial expression analysis and hybrid approaches combining physiological and non-sensor methods, represent the primary strategies for pain detection. Current trends include the adoption of wearable devices, federated learning, and explainable AI. Moreover, sensor technologies play a pivotal role in healthcare by integrating diverse physiological and behavioral data to support automated decision-making, thereby enhancing efficiency and accuracy in pain diagnosis. This study recommends the development of pain detection systems that are more accurate, adaptive, and ethical, as well as clinical trials in real-world settings to improve the validity and acceptance of these technologies in medical practice.
ECG-BASED ARRHYTHMIA DETECTION USING THE NARROW NEURAL NETWORK CLASSIFIER Chandra, Angelia Ayu; Sunnia, Cecilia; Wijaya, Kenrick Alvaro; Dharma, Abdi; Turnip, Arjon; Turnip, Mardi
JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) Vol. 11 No. 2 (2025): JITK Issue November 2025
Publisher : LPPM Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/jitk.v11i2.7121

Abstract

Electrocardiograms (ECG) are important for detecting arrhythmias. Conventional models such as CNN and LSTM are accurate but require large amounts of computation, making them difficult to use on wearable devices and for real-time monitoring. This study evaluates the Narrow Neural Network Classifier (NNNC) as a lightweight and efficient alternative. The dataset consists of 21 subjects with 881 ECG samples, categorized based on walking, sitting, and running activities, and processed through bandpass filtering, normalization, and P-QRS- T wave segmentation. The data is divided into training (70%), validation (15%), and test (15%) sets. The NNNC has 11 convolutional layers, a ReLU activation function, a Softmax output, and 120,000 parameters. The model was trained using the Adam optimizer, a batch size of 32, and a learning rate of 0.001 for 100 epochs and compared with SVM, CNN, and LSTM using accuracy, precision, recall, F1-score, and ROC-AUC. The results show that NNNC achieves an accuracy of 98.9%, a precision of 99.2%, a recall of 99.2%, and an F1-score of 99.2%, higher than SVM and comparable to CNN/LSTM, with lower computational consumption. The model is capable of reliably detecting early arrhythmias. These findings support the potential of NNNC for ECG-based automatic diagnostic systems, including real-time implementation on wearable devices, although further research is needed for large-scale validation
Co-Authors - Afrizal Admin Alief Admin Alif Admin Alif Afriyanti Azhar Alif, Admin Amir Mahmud Husein, Amir Mahmud Andika, Ahmad Zaki Andrian Anggela Marta Tasman Arif Juliari Kusnanda Arjon Turnip Armaini - Baharuddin Shaleh Barus, Samuelta Bayu Afnovandra Perdana Candra, Windy Chandra, Angelia Ayu Chandra, Suwito Christnatalis Chrysia, Celine Crispin, Andrian Reinaldo Dedi Nofiandi Delima Sitanggang, Delima Dewantoro, Rico Wijaya Dicky DS, Jumri Habbeyb Edbert, Edbert Edison Munaf Edison Munaf Elida Mardiah Eri Sulyanti Eti Farda Husin Eti Farda Husin Giawa, Priskila Veronika Hafil Abbas HAFIL ABBAS Harvianti, Yuniar Hazli Nurdin Heyneker, Daniel Hulu, Victor Trismanjaya Husni Mukhtar I PUTU KOMPIANG I. P. Kompiang Indah Indah Indrawati - Indrawati Indrawati IRSAN RYANTO Jabang Nurdin Jamsari Jamsari Jefika, Meliy Kamble, Pratik Bibhisan Kosasi, Hendrick Lazuardya , Kevin Lee Wah Lim Luis, Matthew MARBUN, ADVENT TORAS Mardi Turnip, Mardi MARIA ENDO MAHATA Marniati Salim Mawaddah Harahap, Mawaddah Melona Siska Musifa, Eva Nasril Nasir Nasril Nasir Nasril Nasir Nasril Nasir Nasril Nasir Nurhamidah Oktaf Rina Oktoriza, Ghifarizka Pasaribu, Beriman Periadnadi - Periadnadi Periadnadi Prayogi, Gali PULUNGAN, JURMIDA PURBA, JOICE ANGELINA Putra, Adya Zizwan Rahmadani Wulandari Rahmatika Yani Rahmiana Zein Randi, Albert Refilda Refilda Riska Hernandi Romaito pane, Jesi Saragi, Yosua Morales Sekatresna, Widiyanti Shaleh, Baharuddin Silaban, Elvin Josafat Sirbu, Loredana Ioana Siti Aisyah Siti Hajjir, Siti Sulyanti, Eri Sulyanti, Eri Sumaryati Syukur Sunnia, Cecilia Suryani Suryani Syafriza Yanti Syafrizayanti, Syafrizayanti Syafrizayanti, Syafrizayanti Syafrizayanti, Syafrizayanti Syukri Arief Talib, Ramanisa Muliani Tania, Alinda Tarigan, Julio Putra Toyohide Takeuchi TRIMURTI HABAZAR Turnip, Josua Presen Vagga, Cherry Piya Valentino, Bue Vanness, Jeff Veron, Veron Wahida Nia Elfiza Warni, Mega Waruwu, Jefrin Widiyanti Sekatresna Wijaya, Davin Wijaya, Eko Bambang Wijaya, Jeremy Wijaya, Kenrick Alvaro Wijaya, Vincent William Wizna (Wizna) Wulandari, Rahmadani Yetria Rilda Yohana Samosir, Devi Yose Rizal Yoserizal Yoserizal Yunazar Manjang Yunazar Manjang Yunazar Manjang Zulkarnain Chaidir